Age-related sensitivity to task-related modulation of language-processing networks

Abstract

It is widely assumed that cognitive functions decline with age and that these decrements are associated with age-related changes in patterns of functional activity. However, these functional changes may be due to age-related increased responsiveness to task demands and not to other cognitive processes on which neural and behavioural responses rely, since many ageing studies use task paradigms that may not be orthogonal to the cognitive function being investigated. Here we test this hypothesis in adults aged 20-86 years by combining measures of language comprehension, functional connectivity and neural integrity to identify functional networks activated in two language experiments with varying task demands. In one, participants listened to spoken sentences without performing an overt task (the natural listening condition) while in the other they performed a task in response to the same sentences. Using task-based ICA of fMRI, we identified a left-lateralised frontotemporal network associated with syntactic analysis, which remained consistently activated regardless of task demands. In contrast, in the task condition only a separate set of components showed task-specific activity in Opercular, Frontoparietal, and bilateral PFC. Only the PFC showed age-related increases in activation which, furthermore, was strongly mediated by grey matter health. These results suggest that, contrary to prevailing views, age-related changes in cognitive activation may be due in part to differential responses to task-related processes.

Keywords: Ageing; Functional Networks; ICA; Language; Syntax.

Fig. 1

Schematic of Group ICA analysis pipeline. Boxes indicate major steps in the analysis pipeline, particular choices for the analysis presented here underneath.

Fig. 2

Effects of Task, Language, and Age on each component. A) Frontotemporal, bilateral PFC, Frontoparietal, Opercular, Motor, and Auditory components rendered onto a canonical brain. B) Mean activity for syntactically subordinate, dominant, unambiguous, filler sentences, and acoustic baseline. Asterisks indicate significant effects of Language (greater unacceptable judgements for subordinate compared to dominant) for a particular component within each task condition (task, natural listening; see Table S1C) Age-related correlations across participants (circles; n=25 per task/natural listening conditions), using activity values from the syntactically subordinate sentences. Correlation values (Pearson׳s r) are displayed separately for each experiment (bold: task; light: natural listening). Activation is displayed at FWE corrected p<0.0001, 25 voxels (t>7.9); ^*−p<0.05; ^**−p<0.01.

Fig. 3

Results of the mediation of the age-related increase in bilateral PFC network expression by cortical grey matter. In this model we seek to explain the significant age-related increase in an ICA network comprising bilateral PFC (See Fig. 2C) by proposing grey matter density as a potential mediator. Significant voxels demonstrate either I) the significant relationship between age and grey matter density (a effect), II) the independent relationship between GMD and ICA network expression (b effect), or III) the attenuation of the age-network expression relationship by GMD (ab effect). Significant clusters demonstrating an ab effect (which overlap considerably with the same regions demonstrating age-related increases in activity) therefore help to account for older adults׳ increases task-related activity. Colours are represented from z=1.96 (p=0.05) to z=3.29 (p=0.001); for cluster peaks and z-scores, see Table 3. GMD: grey matter density; ICA: independent component analysis. (For interpretation of the references to colour in this figure, the reader is referred to the web version of this article.)